• arXiv.cs.LG Pub Date : 2020-11-30
Willem van Jaarsveld

Recent literature established that neural networks can represent good MDP policies across a range of stochastic dynamic models in supply chain and logistics. To overcome limitations of the model-free algorithms typically employed to learn/find such neural network policies, a model-based algorithm is proposed that incorporates variance reduction techniques. For the classical lost sales inventory model

更新日期：2020-12-01
• arXiv.cs.LG Pub Date : 2020-11-30
Xuefeng Du; Pengtao Xie

Learning through tests is a broadly used methodology in human learning and shows great effectiveness in improving learning outcome: a sequence of tests are made with increasing levels of difficulty; the learner takes these tests to identify his/her weak points in learning and continuously addresses these weak points to successfully pass these tests. We are interested in investigating whether this powerful

更新日期：2020-12-01
• arXiv.cs.LG Pub Date : 2020-11-30
Anirudh Goyal; Yoshua Bengio

A fascinating hypothesis is that human and animal intelligence could be explained by a few principles (rather than an encyclopedic list of heuristics). If that hypothesis was correct, we could more easily both understand our own intelligence and build intelligent machines. Just like in physics, the principles themselves would not be sufficient to predict the behavior of complex systems like brains

更新日期：2020-12-01
• arXiv.cs.LG Pub Date : 2020-11-30
Rémy Brossard; Oriel Frigo; David Dehaene

Despite quick progress in the last few years, recent studies have shown that modern graph neural networks can still fail at very simple tasks, like detecting small cycles. This hints at the fact that current networks fail to catch information about the local structure, which is problematic if the downstream task heavily relies on graph substructure analysis, as in the context of chemistry. We propose

更新日期：2020-12-01
• arXiv.cs.LG Pub Date : 2020-11-30
Jakub M. Tomczak

In this paper, we present a new class of invertible transformations. We indicate that many well-known invertible tranformations in reversible logic and reversible neural networks could be derived from our proposition. Next, we propose two new coupling layers that are important building blocks of flow-based generative models. In the preliminary experiments on toy digit data, we present how these new

更新日期：2020-12-01
• arXiv.cs.LG Pub Date : 2020-11-30
Runzhong Wang; Tianqi Zhang; Tianshu Yu; Junchi Yan; Xiaokang Yang

Graph Edit Distance (GED) is a popular similarity measurement for pairwise graphs and it also refers to the recovery of the edit path from the source graph to the target graph. Traditional A* algorithm suffers scalability issues due to its exhaustive nature, whose search heuristics heavily rely on human prior knowledge. This paper presents a hybrid approach by combing the interpretability of traditional

更新日期：2020-12-01
• arXiv.cs.LG Pub Date : 2020-11-30
Brady Neal; Chin-Wei Huang; Sunand Raghupathi

There are many different causal effect estimators in causal inference. However, it is unclear how to choose between these estimators because there is no ground-truth for causal effects. A commonly used option is to simulate synthetic data, where the ground-truth is known. However, the best causal estimators on synthetic data are unlikely to be the best causal estimators on realistic data. An ideal

更新日期：2020-12-01
• arXiv.cs.LG Pub Date : 2020-11-30
Hrithwik Shalu; Harikrishnan P; Hari Sankar CN; Akash Das; Saptarshi Majumder; Arnhav Datar; Subin Mathew MS; Anugyan Das; Juned Kadiwala

Preliminary detection of mild depression could immensely help in effective treatment of the common mental health disorder. Due to the lack of proper awareness and the ample mix of stigmas and misconceptions present within the society, mental health status estimation has become a truly difficult task. Due to the immense variations in character level traits from person to person, traditional deep learning

更新日期：2020-12-01
• arXiv.cs.LG Pub Date : 2020-11-26
Jiawei Zhu; Xin Han; Hanhan Deng; Chao Tao; Ling Zhao; Lin Tao; Haifeng Li

When considering the spatial and temporal features of traffic, capturing the impacts of various external factors on travel is an important step towards achieving accurate traffic forecasting. The impacts of external factors on the traffic flow have complex correlations. However, existing studies seldom consider external factors or neglecting the effect of the complex correlations among external factors

更新日期：2020-12-01
• arXiv.cs.LG Pub Date : 2020-11-25
Kamil Deja; Paweł Wawrzyński; Daniel Marczak; Wojciech Masarczyk; Tomasz Trzciński

We introduce a binary latent space autoencoder architecture to rehearse training samples for the continual learning of neural networks. The ability to extend the knowledge of a model with new data without forgetting previously learned samples is a fundamental requirement in continual learning. Existing solutions address it by either replaying past data from memory, which is unsustainable with growing

更新日期：2020-12-01
• arXiv.cs.LG Pub Date : 2020-11-25
Yongquan Yang; Yiming Yang; Jie Chen; Jiayi Zheng; Zhongxi Zheng

Learning from noisy labels is an important concern because of the lack of accurate ground-truth labels in plenty of real-world scenarios. In practice, various approaches for this concern first make corrections corresponding to potentially noisy-labeled instances, and then update predictive model with information of the made corrections. However, in specific areas, such as medical histopathology whole

更新日期：2020-12-01
• arXiv.cs.LG Pub Date : 2020-11-26
Minji Yoon; Théophile Gervet; Bryan Hooi; Christos Faloutsos

Graph data is ubiquitous in academia and industry, from social networks to bioinformatics. The pervasiveness of graphs today has raised the demand for algorithms that can answer various questions: Which products would a user like to purchase given her order list? Which users are buying fake followers to increase their public reputation? Myriads of new graph mining algorithms are proposed every year

更新日期：2020-12-01
• arXiv.cs.LG Pub Date : 2020-11-26

One of the more challenging real-world problems in computational intelligence is to learn from non-stationary streaming data, also known as concept drift. Perhaps even a more challenging version of this scenario is when -- following a small set of initial labeled data -- the data stream consists of unlabeled data only. Such a scenario is typically referred to as learning in initially labeled nonstationary

更新日期：2020-12-01
• arXiv.cs.LG Pub Date : 2020-11-30
Luis Felipe M. O. Henriques; Eduardo Morgan; Sergio Colcher; Ruy Luiz Milidiú

Non-Intrusive Load Monitoring (NILM) is a computational technique to estimate the power loads' appliance-by-appliance from the whole consumption measured by a single meter. In this paper, we propose a conditional density estimation model, based on deep neural networks, that joins a Conditional Variational Autoencoder with a Conditional Invertible Normalizing Flow model to estimate the individual appliance's

更新日期：2020-12-01
• arXiv.cs.LG Pub Date : 2020-11-21
Ian Covert; Scott Lundberg; Su-In Lee

Researchers have proposed a wide variety of model explanation approaches, but it remains unclear how most methods are related or when one method is preferable to another. We establish a new class of methods, removal-based explanations, that are based on the principle of simulating feature removal to quantify each feature's influence. These methods vary in several respects, so we develop a framework

更新日期：2020-12-01
• arXiv.cs.LG Pub Date : 2020-11-30
Derek Lim; René Vidal; Benjamin D. Haeffele

Many state-of-the-art subspace clustering methods follow a two-step process by first constructing an affinity matrix between data points and then applying spectral clustering to this affinity. Most of the research into these methods focuses on the first step of generating the affinity matrix, which often exploits the self-expressive property of linear subspaces, with little consideration typically

更新日期：2020-12-01
• arXiv.cs.LG Pub Date : 2020-11-20
Johan S. Obando-Ceron; Pablo Samuel Castro

Since the introduction of DQN, a vast majority of reinforcement learning research has focused on reinforcement learning with deep neural networks as function approximators. New methods are typically evaluated on a set of environments that have now become standard, such as Atari 2600 games. While these benchmarks help standardize evaluation, their computational cost has the unfortunate side effect of

更新日期：2020-12-01
• arXiv.cs.LG Pub Date : 2020-11-24
Wenyu Zhao; Teli Ma; Xuan Gong; Baochang Zhang; David Doermann

Edge computing is promising to become one of the next hottest topics in artificial intelligence because it benefits various evolving domains such as real-time unmanned aerial systems, industrial applications, and the demand for privacy protection. This paper reviews recent advances on binary neural network (BNN) and 1-bit CNN technologies that are well suitable for front-end, edge-based computing.

更新日期：2020-12-01
• arXiv.cs.LG Pub Date : 2020-11-23
Nicolas Brodu; James P. Crutchfield

We merge computational mechanics' definition of causal states (predictively-equivalent histories) with reproducing-kernel Hilbert space (RKHS) representation inference. The result is a widely-applicable method that infers causal structure directly from observations of a system's behaviors whether they are over discrete or continuous events or time. A structural representation -- a finite- or infinite-state

更新日期：2020-12-01
• arXiv.cs.LG Pub Date : 2020-11-25
Chandra Thapa; M. A. P. Chamikara; Seyit A. Camtepe

In the distributed collaborative machine learning (DCML) paradigm, federated learning (FL) recently attracted much attention due to its applications in health, finance, and the latest innovations such as industry 4.0 and smart vehicles. FL provides privacy-by-design. It trains a machine learning model collaboratively over several distributed clients (ranging from two to millions) such as mobile phones

更新日期：2020-12-01
• arXiv.cs.LG Pub Date : 2020-11-25
Di Liu; Hao Kong; Xiangzhong Luo; Weichen Liu; Ravi Subramaniam

Edge computing and artificial intelligence (AI), especially deep learning for nowadays, are gradually intersecting to build a novel system, called edge intelligence. However, the development of edge intelligence systems encounters some challenges, and one of these challenges is the \textit{computational gap} between computation-intensive deep learning algorithms and less-capable edge systems. Due to

更新日期：2020-12-01
• arXiv.cs.LG Pub Date : 2020-11-30
Jean-Baptiste Truong; Pratyush Maini; Robert Walls; Nicolas Papernot

Current model extraction attacks assume that the adversary has access to a surrogate dataset with characteristics similar to the proprietary data used to train the victim model. This requirement precludes the use of existing model extraction techniques on valuable models, such as those trained on rare or hard to acquire datasets. In contrast, we propose data-free model extraction methods that do not

更新日期：2020-12-01
• arXiv.cs.LG Pub Date : 2020-11-30
Peter Bellmann; Heinke Hihn; Daniel A. Braun; Friedhelm Schwenker

In many real-world pattern recognition scenarios, such as in medical applications, the corresponding classification tasks can be of an imbalanced nature. In the current study, we focus on binary, imbalanced classification tasks, i.e.~binary classification tasks in which one of the two classes is under-represented (minority class) in comparison to the other class (majority class). In the literature

更新日期：2020-12-01
• arXiv.cs.LG Pub Date : 2020-11-30
Verónica Álvarez; Santiago Mazuelas; José A. Lozano

Load forecasting is crucial for multiple energy management tasks such as scheduling generation capacity, planning supply and demand, and minimizing energy trade costs. Such relevance has increased even more in recent years due to the integration of renewable energies, electric cars, and microgrids. Conventional load forecasting techniques obtain single-value load forecasts by exploiting consumption

更新日期：2020-12-01
• arXiv.cs.LG Pub Date : 2020-11-30
Akshay L Chandra; Sai Vikas Desai; Chaitanya Devaguptapu; Vineeth N Balasubramanian

Active Learning (AL) techniques aim to minimize the training data required to train a model for a given task. Pool-based AL techniques start with a small initial labeled pool and then iteratively pick batches of the most informative samples for labeling. Generally, the initial pool is sampled randomly and labeled to seed the AL iterations. While recent studies have focused on evaluating the robustness

更新日期：2020-12-01
• arXiv.cs.LG Pub Date : 2020-11-30
Het Shah; Avishree Khare; Neelay Shah; Khizir Siddiqui

In recent years, the growing size of neural networks has led to a vast amount of research concerning compression techniques to mitigate the drawbacks of such large sizes. Most of these research works can be categorized into three broad families : Knowledge Distillation, Pruning, and Quantization. While there has been steady research in this domain, adoption and commercial usage of the proposed techniques

更新日期：2020-12-01
• arXiv.cs.LG Pub Date : 2020-11-30
Guido Montúfar; Nina Otter; Yuguang Wang

Topological data analysis uses tools from topology -- the mathematical area that studies shapes -- to create representations of data. In particular, in persistent homology, one studies one-parameter families of spaces associated with data, and persistence diagrams describe the lifetime of topological invariants, such as connected components or holes, across the one-parameter family. In many applications

更新日期：2020-12-01
• arXiv.cs.LG Pub Date : 2020-11-30
Simone Angarano; Vittorio Mazzia; Francesco Salvetti; Giovanni Fantin; Marcello Chiaberge

Ultra-wideband (UWB) is the state-of-the-art and most popular technology for wireless localization. Nevertheless, precise ranging and localization in non-line-of-sight (NLoS) conditions is still an open research topic. Indeed, multipath effects, reflections, refractions and complexity of the indoor radio environment can easily introduce a positive bias in the ranging measurement, resulting in highly

更新日期：2020-12-01
• arXiv.cs.LG Pub Date : 2020-11-30
Xu Chen; Yuanxing Zhang; Lun Du; Zheng Fang; Yi Ren; Kaigui Bian; Kunqing Xie

Traffic flow forecasting is of great significance for improving the efficiency of transportation systems and preventing emergencies. Due to the highly non-linearity and intricate evolutionary patterns of short-term and long-term traffic flow, existing methods often fail to take full advantage of spatial-temporal information, especially the various temporal patterns with different period shifting and

更新日期：2020-12-01
• arXiv.cs.LG Pub Date : 2020-11-30
N. Mazyavkina; S. Moustafa; I. Trofimov; E. Burnaev

Reinforcement learning (RL) enjoyed significant progress over the last years. One of the most important steps forward was the wide application of neural networks. However, architectures of these neural networks are typically constructed manually. In this work, we study recently proposed neural architecture search (NAS) methods for optimizing the architecture of RL agents. We carry out experiments on

更新日期：2020-12-01
• arXiv.cs.LG Pub Date : 2020-11-30
Maciej Zięba; Marcin Przewięźlikowski; Marek Śmieja; Jacek Tabor; Tomasz Trzcinski; Przemysław Spurek

Predicting future states or actions of a given system remains a fundamental, yet unsolved challenge of intelligence, especially in the scope of complex and non-deterministic scenarios, such as modeling behavior of humans. Existing approaches provide results under strong assumptions concerning unimodality of future states, or, at best, assuming specific probability distributions that often poorly fit

更新日期：2020-12-01
• arXiv.cs.LG Pub Date : 2020-11-30
Ziyang Wu; Christina Baek; Chong You; Yi Ma

Current deep learning architectures suffer from catastrophic forgetting, a failure to retain knowledge of previously learned classes when incrementally trained on new classes. The fundamental roadblock faced by deep learning methods is that deep learning models are optimized as "black boxes," making it difficult to properly adjust the model parameters to preserve knowledge about previously seen data

更新日期：2020-12-01
• arXiv.cs.LG Pub Date : 2020-11-30
Badih Ghazi; Ravi Kumar; Pasin Manurangsi; Thao Nguyen

In this work, we study the trade-off between differential privacy and adversarial robustness under L2-perturbations in the context of learning halfspaces. We prove nearly tight bounds on the sample complexity of robust private learning of halfspaces for a large regime of parameters. A highlight of our results is that robust and private learning is harder than robust or private learning alone. We complement

更新日期：2020-12-01
• arXiv.cs.LG Pub Date : 2020-11-30
Stone Yun; Alexander Wong

With the proliferation of deep convolutional neural network (CNN) algorithms for mobile processing, limited precision quantization has become an essential tool for CNN efficiency. Consequently, various works have sought to design fixed precision quantization algorithms and quantization-focused optimization techniques that minimize quantization induced performance degradation. However, there is little

更新日期：2020-12-01
• arXiv.cs.LG Pub Date : 2020-11-30

We use gradient sparsification to reduce the adverse effect of differential privacy noise on performance of private machine learning models. To this aim, we employ compressed sensing and additive Laplace noise to evaluate differentially-private gradients. Noisy privacy-preserving gradients are used to perform stochastic gradient descent for training machine learning models. Sparsification, achieved

更新日期：2020-12-01
• arXiv.cs.LG Pub Date : 2020-11-30
Jeong-Hoe Ku; JiHun Oh; YoungYoon Lee; Gaurav Pooniwala; SangJeong Lee

This paper aims to provide a selective survey about knowledge distillation(KD) framework for researchers and practitioners to take advantage of it for developing new optimized models in the deep neural network field. To this end, we give a brief overview of knowledge distillation and some related works including learning using privileged information(LUPI) and generalized distillation(GD). Even though

更新日期：2020-12-01
• arXiv.cs.LG Pub Date : 2020-11-30
Greg Yang; Edward J. Hu

As its width tends to infinity, a deep neural network's behavior under gradient descent can become simplified and predictable (e.g. given by the Neural Tangent Kernel (NTK)), if it is parametrized appropriately (e.g. the NTK parametrization). However, we show that the standard and NTK parametrizations of a neural network do not admit infinite-width limits that can learn features, which is crucial for

更新日期：2020-12-01
• arXiv.cs.LG Pub Date : 2020-11-30

In reinforcement learning, robust policies for high-stakes decision-making problems with limited data are usually computed by optimizing the percentile criterion, which minimizes the probability of a catastrophic failure. Unfortunately, such policies are typically overly conservative as the percentile criterion is non-convex, difficult to optimize, and ignores the mean performance. To overcome these

更新日期：2020-12-01
• arXiv.cs.LG Pub Date : 2020-11-30
Benoit Steiner; Chris Cummins; Horace He; Hugh Leather

As machine learning techniques become ubiquitous, the efficiency of neural network implementations is becoming correspondingly paramount. Frameworks, such as Halide and TVM, separate out the algorithmic representation of the network from the schedule that determines its implementation. Finding good schedules, however, remains extremely challenging. We model this scheduling problem as a sequence of

更新日期：2020-12-01
• arXiv.cs.LG Pub Date : 2020-11-30
Gabriel S. Gusmão; Adhika P. Retnanto; Shashwati C. da Cunha; Andrew J. Medford

Chemical kinetics consists of the phenomenological framework for the disentanglement of reaction mechanisms, optimization of reaction performance and the rational design of chemical processes. Here, we utilize feed-forward artificial neural networks as basis functions for the construction of surrogate models to solve ordinary differential equations (ODEs) that describe microkinetic models (MKMs). We

更新日期：2020-12-01
• arXiv.cs.LG Pub Date : 2020-11-29
Sam Greydanus

Though deep learning models have taken on commercial and political relevance, many aspects of their training and operation remain poorly understood. This has sparked interest in "science of deep learning" projects, many of which are run at scale and require enormous amounts of time, money, and electricity. But how much of this research really needs to occur at scale? In this paper, we introduce MNIST-1D:

更新日期：2020-12-01
• arXiv.cs.LG Pub Date : 2020-11-29
George Cazenavette; Calvin Murdock; Simon Lucey

Despite their unmatched performance, deep neural networks remain susceptible to targeted attacks by nearly imperceptible levels of adversarial noise. While the underlying cause of this sensitivity is not well understood, theoretical analyses can be simplified by reframing each layer of a feed-forward network as an approximate solution to a sparse coding problem. Iterative solutions using basis pursuit

更新日期：2020-12-01
• arXiv.cs.LG Pub Date : 2020-11-29
Weijun Luo

Neural network forms the foundation of deep learning and numerous AI applications. Classical neural networks are fully connected, expensive to train and prone to overfitting. Sparse networks tend to have convoluted structure search, suboptimal performance and limited usage. We proposed the novel uniform sparse network (USN) with even and sparse connectivity within each layer. USN has one striking property

更新日期：2020-12-01
• arXiv.cs.LG Pub Date : 2020-11-29
Andrii Zadaianchuk; Maximilian Seitzer; Georg Martius

Autonomous agents need large repertoires of skills to act reasonably on new tasks that they have not seen before. However, acquiring these skills using only a stream of high-dimensional, unstructured, and unlabeled observations is a tricky challenge for any autonomous agent. Previous methods have used variational autoencoders to encode a scene into a low-dimensional vector that can be used as a goal

更新日期：2020-12-01
• arXiv.cs.LG Pub Date : 2020-11-29
Louis Monier; Jakub Kmec; Alexandre Laterre; Thomas Pierrot; Valentin Courgeau; Olivier Sigaud; Karim Beguir

Offline Reinforcement Learning (RL) aims to turn large datasets into powerful decision-making engines without any online interactions with the environment. This great promise has motivated a large amount of research that hopes to replicate the success RL has experienced in simulation settings. This work ambitions to reflect upon these efforts from a practitioner viewpoint. We start by discussing the

更新日期：2020-12-01
• arXiv.cs.LG Pub Date : 2020-11-29
Hadia Mohmmed Osman Ahmed Samil; Annabelle Martin; Arnav Kumar Jain; Susan Amin; Samira Ebrahimi Kahou

Locust infestation of some regions in the world, including Africa, Asia and Middle East has become a concerning issue that can affect the health and the lives of millions of people. In this respect, there have been attempts to resolve or reduce the severity of this problem via detection and monitoring of locust breeding areas using satellites and sensors, or the use of chemicals to prevent the formation

更新日期：2020-12-01
• arXiv.cs.LG Pub Date : 2020-11-29
Sarah; S. Sidhartha Narayan; Irfaan Arif; Hrithwik Shalu; Juned Kadiwala

We suggest a low cost, non invasive healthcare system that measures haemoglobin levels in patients and can be used as a preliminary diagnostic test for anaemia. A combination of image processing, machine learning and deep learning techniques are employed to develop predictive models to measure haemoglobin levels. This is achieved through the color analysis of the fingernail beds, palpebral conjunctiva

更新日期：2020-12-01
• arXiv.cs.LG Pub Date : 2020-11-29
Jiazhu Dai; Weifeng Zhu; Xiangfeng Luo

Graph-structured data exist in numerous applications in real life. As a state-of-the-art graph neural network, the graph convolutional network (GCN) plays an important role in processing graph-structured data. However, a recent study reported that GCNs are also vulnerable to adversarial attacks, which means that GCN models may suffer malicious attacks with unnoticeable modifications of the data. Among

更新日期：2020-12-01
• arXiv.cs.LG Pub Date : 2020-11-29
Jinlin Lai; Lixin Zou; Jiaxing Song

Off-policy evaluation is a key component of reinforcement learning which evaluates a target policy with offline data collected from behavior policies. It is a crucial step towards safe reinforcement learning and has been used in advertisement, recommender systems and many other applications. In these applications, sometimes the offline data is collected from multiple behavior policies. Previous works

更新日期：2020-12-01
• arXiv.cs.LG Pub Date : 2020-11-29
Arindam Bhattacharya; Sumanth Varambally; Amitabha Bagchi; Srikanta Bedathur

We present Fast Random projection-based One-Class Classification (FROCC), an extremely efficient method for one-class classification. Our method is based on a simple idea of transforming the training data by projecting it onto a set of random unit vectors that are chosen uniformly and independently from the unit sphere, and bounding the regions based on separation of the data. FROCC can be naturally

更新日期：2020-12-01
• arXiv.cs.LG Pub Date : 2020-11-29

Active learning shows promise to decrease test bench time for model-based drivability calibration. This paper presents a new strategy for active output selection, which suits the needs of calibration tasks. The strategy is actively learning multiple outputs in the same input space. It chooses the output model with the highest cross-validation error as leading. The presented method is applied to three

更新日期：2020-12-01
• arXiv.cs.LG Pub Date : 2020-11-29
Qiwen Cui; Lin F. Yang

The empirical success of Multi-agent reinforcement learning is encouraging, while few theoretical guarantees have been revealed. In this work, we prove that the plug-in solver approach, probably the most natural reinforcement learning algorithm, achieves minimax sample complexity for turn-based stochastic game (TBSG). Specifically, we plan in an empirical TBSG by utilizing a simulator' that allows

更新日期：2020-12-01
• arXiv.cs.LG Pub Date : 2020-11-29
Hongseok Namkoong; Samuel Daulton; Eytan Bakshy

Thompson sampling (TS) has emerged as a robust technique for contextual bandit problems. However, TS requires posterior inference and optimization for action generation, prohibiting its use in many internet applications where latency and ease of deployment are of concern. We propose a novel imitation-learning-based algorithm that distills a TS policy into an explicit policy representation by performing

更新日期：2020-12-01
• arXiv.cs.LG Pub Date : 2020-11-29

We study generalization under label shift in domain adaptation where the learner has access to labeled samples from the source domain but unlabeled samples from the target domain. Prior works deploy label classifiers and introduce various methods to estimate the importance weights from source to target domains. They use these estimates in importance weighted empirical risk minimization to learn classifiers

更新日期：2020-12-01
• arXiv.cs.LG Pub Date : 2020-11-29
Elana Kozak; Scott Hottovy

Monte Carlo Tree Search (MCTS) is a branch of stochastic modeling that utilizes decision trees for optimization, mostly applied to artificial intelligence (AI) game players. This project imagines a game in which an AI player searches for a stationary target within a 2-D lattice. We analyze its behavior with different target distributions and compare its efficiency to the Levy Flight Search, a model

更新日期：2020-12-01
• arXiv.cs.LG Pub Date : 2020-11-28
Hongbin Pei; Bingzhe Wei; Kevin Chen-Chuan Chang; Chunxu Zhang; Bo Yang

Recent research on graph embedding has achieved success in various applications. Most graph embedding methods preserve the proximity in a graph into a manifold in an embedding space. We argue an important but neglected problem about this proximity-preserving strategy: Graph topology patterns, while preserved well into an embedding manifold by preserving proximity, may distort in the ambient embedding

更新日期：2020-12-01
• arXiv.cs.LG Pub Date : 2020-11-28
Richard Archibald; Feng Bao; Yanzhao Cao; He Zhang

We develop a probabilistic machine learning method, which formulates a class of stochastic neural networks by a stochastic optimal control problem. An efficient stochastic gradient descent algorithm is introduced under the stochastic maximum principle framework. Convergence analysis for stochastic gradient descent optimization and numerical experiments for applications of stochastic neural networks

更新日期：2020-12-01
• arXiv.cs.LG Pub Date : 2020-11-28
Abdul Wahab; Muhammad Anas Tahir; Naveed Iqbal; Faisal Shafait; Syed Muhammad Raza Kazmi

Electricity load forecasting enables the grid operators to optimally implement the smart grid's most essential features such as demand response and energy efficiency. Electricity demand profiles can vary drastically from one region to another on diurnal, seasonal and yearly scale. Hence to devise a load forecasting technique that can yield the best estimates on diverse datasets, specially when the

更新日期：2020-12-01
• arXiv.cs.LG Pub Date : 2020-11-28
Zakaria Mhammedi; Hisham Husain

Acquisition of data is a difficult task in most applications of Machine Learning (ML), and it is only natural that one hopes and expects lower populating risk (better performance) with increasing data points. It turns out, somewhat surprisingly, that this is not the case even for the most standard algorithms such as the Empirical Risk Minimizer (ERM). Non-monotonic behaviour of the risk and instability

更新日期：2020-12-01
• arXiv.cs.LG Pub Date : 2020-11-28
Johannes Klicpera; Shankari Giri; Johannes T. Margraf; Stephan Günnemann

Many important tasks in chemistry revolve around molecules during reactions. This requires predictions far from the equilibrium, while most recent work in machine learning for molecules has been focused on equilibrium or near-equilibrium states. In this paper we aim to extend this scope in three ways. First, we propose the DimeNet++ model, which is 8x faster and 10% more accurate than the original

更新日期：2020-12-01
Contents have been reproduced by permission of the publishers.

down
wechat
bug